CN110378971A - A kind of detection method and device of image alignment precision, equipment, storage medium - Google Patents
A kind of detection method and device of image alignment precision, equipment, storage medium Download PDFInfo
- Publication number
- CN110378971A CN110378971A CN201910678583.6A CN201910678583A CN110378971A CN 110378971 A CN110378971 A CN 110378971A CN 201910678583 A CN201910678583 A CN 201910678583A CN 110378971 A CN110378971 A CN 110378971A
- Authority
- CN
- China
- Prior art keywords
- image
- characteristic point
- rgb
- coordinate system
- mapped
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the present application discloses the detection method and equipment, storage medium of a kind of image alignment precision, wherein, the described method includes: obtaining tested equipment to the shooting result of the test pattern in detection device, wherein, the shooting result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;It is mapped to the three-dimensional coordinate in rgb pixel coordinate system according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image, determines the image alignment precision of the tested equipment.
Description
Technical field
The invention relates to electronic technology, relate to, but are not limited to the detection method and dress of a kind of image alignment precision
It sets, equipment, storage medium.
Background technique
One RGBD (Red Green Blue Depth, red green blue depth) system includes depth camera and coloured silk
Color RGB (Red Green Blue, red green blue) camera, depth camera are responsible for providing Z-direction range information, and RGB camera is then
It is responsible for providing texture and colouring information.Alignment calibration would generally be carried out to the RGBD camera when RGBD camera is produced,
The relative positional relationship of RGB camera and depth camera is obtained, is answered so that the later period completes RGB image with what depth image blended
With.But there is no a kind of accuracy checking methods of simple, efficient image alignment calibration therefore how to guarantee the later period at present
How the accuracy that depth image is aligned with RGB image in is examined calibration effect that is, after the completion of being aligned calibration
It surveys, to ensure product consistency and later period application effect, becomes those skilled in the art's technical problem urgently to be resolved.
Summary of the invention
In view of this, detection method and device, equipment, storage that the embodiment of the present application provides a kind of image alignment precision are situated between
Matter.
The technical solution of the embodiment of the present application is achieved in that
In a first aspect, the embodiment of the present application provides a kind of detection method of image alignment precision, which comprises
Tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting result includes:
Infrared IR (Infrared Radiation, infrared ray) image, color RGB image and depth image have on the test pattern
Pre-set characteristic point;
According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to
Three-dimensional coordinate in rgb pixel coordinate system;
Rgb pixel is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image to sit
Three-dimensional coordinate in mark system, determines the image alignment precision of the tested equipment.
In the embodiment of the present application, the characteristic point according in the IR image and the depth image determine the IR
Characteristic point in image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, comprising:
Determine the characteristic point in the IR image;
According to the internal structure parameter of the tested equipment of acquisition and the depth image, the spy in the IR image is determined
The three-dimensional coordinate that sign point is mapped in rgb pixel coordinate system.
Spy in the embodiment of the present application, in the coordinate and the IR image according to the characteristic point in the RGB image
The three-dimensional coordinate that sign point is mapped in rgb pixel coordinate system, determines the image alignment precision of the tested equipment, comprising:
Determine characteristic point corresponding with the IR image in the RGB image;
The coordinate and the characteristic point in the IR image for determining the corresponding characteristic point are mapped in rgb pixel coordinate system
Three-dimensional coordinate difference;
According to the difference, the image alignment precision of the tested equipment is determined.
In the embodiment of the present application, the internal structure parameter of the tested equipment according to acquisition and the depth image,
Determine that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, comprising:
Using the depth image, the corresponding depth value of characteristic point in the IR image is determined;
According to the internal structure parameter of the tested equipment of acquisition and the depth value, the feature in the IR image is determined
The three-dimensional coordinate that point is mapped in rgb pixel coordinate system.
In the embodiment of the present application, the internal structure parameter of the tested equipment according to acquisition and the depth value, really
Characteristic point in the fixed IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, comprising:
According to the first structure parameter of acquisition and the depth value, determine that the characteristic point in the IR image is sat in IR camera
Three-dimensional coordinate in mark system;Wherein, the first structure parameter, for showing between IR pixel coordinate system and IR camera coordinates system
Projection relation;
According to three-dimensional seat of the characteristic point in the second structural parameters of acquisition and the IR image in IR camera coordinates system
Mark, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in RGB camera coordinate system;Second structural parameters,
For showing the projection relation between IR camera coordinates system and RGB camera coordinate system;
Three be mapped to according to the characteristic point in the third structural parameters of acquisition and the IR image in RGB camera coordinate system
Coordinate is tieed up, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;The third structure ginseng
Number is for showing the projection relation between rgb pixel coordinate system and RGB camera coordinate system.
In the embodiment of the present application, after the characteristic point in the determination IR image, the method also includes:
Using the IR distortion parameter of acquisition, distortion is carried out to the characteristic point in the IR image and is handled;Wherein, the IR
Distortion parameter is the corresponding camera distortion parameter of IR image;
Accordingly, in the determination RGB image after characteristic point corresponding with the IR image, the method is also wrapped
It includes:
Using the RGB distortion parameter of acquisition, distortion is carried out to the characteristic point in the RGB image and is handled;Wherein, described
RGB distortion parameter is the corresponding camera distortion parameter of RGB image.
It is described that the image alignment precision of the tested equipment is determined according to the difference in the embodiment of the present application, packet
It includes:
According to the difference of all characteristic points, the corresponding standard deviation of the difference of all characteristic points, average value and maximum value are determined;
According to the standard deviation, average value and maximum value, the image alignment precision of the tested equipment is determined.
Second aspect, the embodiment of the present application provide a kind of detection device of image alignment precision, and described device includes:
Acquiring unit, for obtaining tested equipment to the shooting result of the test pattern in detection device, wherein described
Shooting result includes: IR image, RGB image and depth image, there is pre-set characteristic point on the test pattern;
First determination unit, for according in the IR image characteristic point and the depth image, determine IR figure
Characteristic point as in is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Second determination unit, for the feature in the coordinate and the IR image according to the characteristic point in the RGB image
The three-dimensional coordinate that point is mapped in rgb pixel coordinate system, determines the image alignment precision of the tested equipment.
The third aspect, the embodiment of the present application provide a kind of detection device, and the detection device includes:
Test suite is contacted with backlight, and the test pattern being pre-designed is provided on the test suite, so that working as
When tested equipment shoots the test pattern, the detection device can be realized the image alignment essence to the tested equipment
Spend the function of detection;
Backlight enables the tested equipment to obtain the test pattern for issuing visible or infrared light
IR image, RGB image and depth image;
Processor, for executing following steps:
Tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting result includes:
IR image, RGB image and depth image have pre-set characteristic point on the test pattern;
According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to
Three-dimensional coordinate in rgb pixel coordinate system;
Rgb pixel is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image to sit
Three-dimensional coordinate in mark system, determines the image alignment precision of the tested equipment.
In the embodiment of the present application, it is provided with and is pre-designed on the first face for being contacted on the test suite with the backlight
Test pattern, second face opposite with the contact surface has diffusing characteristic diffuser on the test suite.
Fourth aspect, the embodiment of the present application provide a kind of detection device, including memory and processor, and the memory is deposited
The computer program that can be run on a processor is contained, the processor realizes image alignment as described above when executing described program
Step in the detection method of precision.
5th aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer program,
The computer program realizes the step in the detection method of image alignment precision as described above when being executed by processor.
The embodiment of the present application provides a kind of detection method and device of image alignment precision, equipment, storage medium, by obtaining
Take tested equipment to the shooting result of the test pattern in detection device, wherein the shooting result includes: infrared IR figure
As, color RGB image and depth image, there is pre-set characteristic point on the test pattern;According in the IR image
Characteristic point and the depth image determine that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
It is mapped in rgb pixel coordinate system according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
Three-dimensional coordinate determines the image alignment precision of the tested equipment, so, it is possible to provide a kind of applicability extensive, high-efficient
Image alignment accuracy checking method, while providing image alignment precision testing device that is a kind of simple, being conducive to batch production.
Detailed description of the invention
Figure 1A is the workflow schematic diagram of structure light;
Figure 1B is the work process result schematic diagram of structure light;
Fig. 2A is the implementation process schematic diagram one of the detection method of the embodiment of the present application image alignment precision;
Fig. 2 B is the implementation process schematic diagram two of the detection method of the embodiment of the present application image alignment precision;
Fig. 2 C is the implementation process schematic diagram three of the detection method of the embodiment of the present application image alignment precision;
Fig. 3 is the implementation process schematic diagram four of the detection method of the embodiment of the present application image alignment precision;
Fig. 4 is the composed structure schematic diagram of the detection device of the embodiment of the present application image alignment precision;
Fig. 5 is the composed structure schematic diagram one of the embodiment of the present application detection device;
Fig. 6 is the composed structure schematic diagram two of the embodiment of the present application detection device;
Fig. 7 is a kind of hardware entities schematic diagram of the embodiment of the present application detection device.
Specific embodiment
Generally, depth image is also referred to as range image, refers to the distance of each point in from image acquisition device to scene
The image of (i.e. depth) as pixel value, it directly reflects the geometry of scenery visible surface.Depth image passes through coordinate
Conversion may be calculated point cloud data, and regular and necessary information point cloud data can also be using inverse as depth image data.
It after the specific optical information to body surface of project structured light, is acquired by camera, the optical signal according to caused by object
Variation come information such as the position and the depth that calculate object, then restore entire three-dimensional space.Figure 1A is the workflow of structure light
Schematic diagram, as shown in Figure 1A, structure light workflow are as follows: first, the infrared speckle field 11 of laser projection mould group projection to 3D
The surface of (3Dimensions, three-dimensional) object 12.The second, infrared photosensitive mould group acquires black and white pattern 13, is sent into ASIC
Depth calculation is carried out in (Application Specific Integrated Circuit, specific integrated circuit) chip.The
Three, chip exports deep video stream information 14.Figure 1B is the work process result schematic diagram of structure light, as shown in Figure 1B, image
11 speckle patterns acquired for structure light receiving module, i.e., infrared IR image.The speckle pattern of image 12 is by being calculated
Depth map.
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the specific technical solution of application is described in further detail.The following examples are only for illustrating the present application, does not have to
In limitation scope of the present application.
In subsequent description, it is only using the suffix for indicating such as " module ", " component " or " unit " of element
The explanation for being conducive to the application, itself does not have a specific meaning.Therefore, " module ", " component " or " unit " can mix
Ground uses.
The embodiment of the present application provides a kind of detection method of image alignment precision, and this method is applied to detection device, the party
The function that method is realized can realize that certain program code can be saved by the processor caller code in server
In computer storage medium, it is seen then that the server includes at least pocessor and storage media.Fig. 2A is the embodiment of the present application figure
As the implementation process schematic diagram one of the detection method of alignment accuracy, as shown in Figure 2 A, which comprises
Step S201, tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;
Here, the tested equipment can be RGBD equipment, such as RGBD camera, can shoot color RGB image,
Depth image can also be shot.RGBD camera according to working principle can be divided into three kinds: TOF (Time of flight flies at present
Row time telemetry), RGB binocular and structure light.Wherein, the distance measuring method of TOF types of cameras is active, is flown according to light
The row time directly measures distance.The distance measuring method of RGB binocular types of cameras be passive type, be according to RGB image Feature Points Matching,
Triangulation calculates distance indirectly.The distance measuring method of structure light types of cameras is active, is according to actively projecting known coded
Pattern, lifting feature matching effect calculate distance.In this way, after RGBD equipment shoots test pattern, so that it may obtain
Take infrared IR image, color RGB image and depth image.
In the embodiment of the present application, the test pattern is the test pattern being set in advance in detection device, wherein described
There are pre-set characteristic point, i.e. mark point on test pattern.In this way, being obtained after RGBD equipment shoots test pattern
To infrared IR image, in color RGB image and depth image, can all have the characteristic point, by three kinds of different types
Image on characteristic point relevant operation, so that it may realize the detection of the image alignment precision of the RGBD equipment.
Step S202, according in the IR image characteristic point and the depth image, determine the spy in the IR image
The three-dimensional coordinate that sign point is mapped in rgb pixel coordinate system;
Here, when the RGBD equipment is structure light type, since 3D structure light is that will have by near infrared laser
There is the light of certain structure feature to project on subject, then is acquired by special infrared camera, it is therefore, described
IR image is the speckle pattern acquired in the structure light course of work by infrared camera.
Similarly, when the RGBD equipment be TOF type when, due to TOF be emitted by infrared transmitter it is modulated
Light pulse after encountering object reflection, receives reflected light pulse with receiver, and calculate according to the two-way time of light pulse
The distance between object, therefore, the IR image are the infrared image obtained in the TOF course of work by TOF camera.
Step S203, it is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
Three-dimensional coordinate in rgb pixel coordinate system determines the image alignment precision of the tested equipment.
Here, image is all made of pixel, and pixel coordinate is the position of pixel in the picture.Common coordinate system has
Image coordinate system, camera coordinates system, world coordinate system etc..Wherein, it can mutually be converted between different coordinates, it is same
Coordinate position of the point in different coordinates can mutually map.Described image coordinate system is using the image upper left corner as origin
Establish the direct coordinate system u-v as unit of pixel.The abscissa u and ordinate v of pixel are the institute in its image array respectively
Columns and place line number.Xc of the camera coordinates system with camera optical center (i.e. projection centre) for origin, in camera coordinates system
Axis and Yc axis are parallel with the x-axis of imaging plane coordinate system and y-axis, and Zc axis is vertical for the optical axis and the plane of delineation of video camera.
In the embodiment of the present application, the characteristic point in IR image can be mapped in rgb pixel coordinate system, after mapping
Three-dimensional coordinate is compared with the coordinate of the characteristic point in RGB image, to determine the tested equipment (such as RGBD camera)
Image alignment precision.
In the embodiment of the present application, by obtaining tested equipment to the shooting result of the test pattern in detection device,
In, the shooting result includes: infrared IR image, color RGB image and depth image, is preset on the test pattern
Characteristic point;According in the IR image characteristic point and the depth image, determine in the IR image characteristic point mapping
To the three-dimensional coordinate in rgb pixel coordinate system;According to the spy in the coordinate of the characteristic point in the RGB image and the IR image
The three-dimensional coordinate that sign point is mapped in rgb pixel coordinate system, determines the image alignment precision of the tested equipment, in this way, mentioning
The image alignment accuracy checking method extensive, high-efficient for a kind of applicability.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection method of image alignment precision, the side again
Method includes:
Step S211, tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;
Step S212, the characteristic point in the IR image is determined;
Step S213, according to the internal structure parameter of the tested equipment of acquisition and the depth image, the IR is determined
Characteristic point in image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Here, when the tested equipment is RGBD camera, the internal structure parameter of the tested equipment can be
The internal reference of camera, outer ginseng and distortion parameter.The internal reference, outer ginseng and distortion parameter are determined by camera itself, Bu Huiyin
Change for external environment.The internal reference mainly includes focal length and picture element density of camera etc..The outer ginseng, it is main to wrap
The rotation parameter of three axis and the translation parameters of three axis have been included, has been the key that be transformed into calibration coordinate.The distortion parameter, it is main
It include radial distortion parameter and tangential distortion coefficient, wherein radial distortion occurs in camera coordinates system image rotation physical coordinates
During system, tangential distortion Producing reason is that lens are not exclusively parallel to image.
Step S214, it is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
Three-dimensional coordinate in rgb pixel coordinate system determines the image alignment precision of the tested equipment.
In the embodiment of the present application, the characteristic point in IR image, then the equipment by shooting the IR image can be first determined
Internal structure parameter, and shooting depth image, determine that the characteristic point in the IR image is mapped to rgb pixel coordinate
Three-dimensional coordinate in system, in this manner it is possible to which it is compared (in the RGB image with the coordinate of the characteristic point in RGB image
The coordinate of characteristic point be located at rgb pixel coordinate system), so that it is determined that the image alignment precision of the RGBD equipment.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection method of image alignment precision again, and Fig. 2 B is
The implementation process schematic diagram two of the detection method of the embodiment of the present application image alignment precision, as shown in Figure 2 B, which comprises
Step S221, tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;
In the embodiment of the present application, the test pattern is the test pattern being set in advance in detection device, wherein described
There are pre-set characteristic point, i.e. mark point on test pattern.In this way, being obtained after RGBD equipment shoots test pattern
To infrared IR image, in color RGB image and depth image, can all have the characteristic point, by three kinds of different types
Image on characteristic point relevant operation, so that it may realize the detection of the image alignment precision of the RGBD equipment.
Step S222, the characteristic point in the IR image is determined;
Step S223, according to the internal structure parameter of the tested equipment of acquisition and the depth image, the IR is determined
Characteristic point in image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Step S224, characteristic point corresponding with the IR image in the RGB image is determined;
In the embodiment of the present application, there is pre-set N number of characteristic point on the test pattern, N is the nature more than or equal to 1
Number.After the RGBD equipment shoots test pattern, obtained infrared IR image, color RGB image and depth image
In, can all there be N number of characteristic point.When by i-th (i is the natural number less than or equal to N more than or equal to 1) in IR image
Characteristic point is mapped in rgb pixel coordinate system, when obtaining its three-dimensional coordinate in rgb pixel coordinate system, so that it may be continued true
Ith feature point described in the fixed RGB image.That is, feature corresponding with the IR image in the RGB image
Point refers to an identical characteristic point in test image.
Step S225, the coordinate and the characteristic point in the IR image for determining the corresponding characteristic point are mapped to RGB picture
The difference of three-dimensional coordinate in plain coordinate system;
Here, after determining an identical characteristic point in RGB image, continue the coordinate for determining the characteristic point, and will
The coordinate of characteristic point described in RGB image is compared with the coordinate of the characteristic point after mapping in IR image, calculates the coordinate
Difference determine the image alignment precision of the tested equipment and according to the difference.
Step S226, according to the difference, the image alignment precision of the tested equipment is determined.
In the embodiment of the present application, there is pre-set N number of characteristic point on the test pattern, therefore, the difference includes
The difference of the coordinate of characteristic point after multiple mappings, and then can be come true by the difference of the coordinate of the multiple characteristic point
The image alignment precision of the fixed tested equipment.
In the embodiment of the present application, by obtaining tested equipment to the shooting result of the test pattern in detection device,
In, the shooting result includes: infrared IR image, color RGB image and depth image, is preset on the test pattern
Characteristic point;Determine the characteristic point in the IR image;According to the internal structure parameter and the depth of the tested equipment of acquisition
Image is spent, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;Determine the RGB figure
The characteristic point corresponding with the IR image as in;The coordinate for determining the corresponding characteristic point and the characteristic point in the IR image
It is mapped to the difference of the three-dimensional coordinate in rgb pixel coordinate system;According to the difference, the image pair of the tested equipment is determined
Neat precision, in this way, providing the image alignment accuracy checking method that a kind of applicability is extensive, high-efficient.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection method of image alignment precision, the side again
Method includes:
Step S231, tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;
Step S232, the characteristic point in the IR image is determined;
Step S233, using the depth image, the corresponding depth value of characteristic point in the IR image is determined;
In the embodiment of the present application, there is pre-set N number of characteristic point on the test pattern, N is the nature more than or equal to 1
Number.After the RGBD equipment shoots test pattern, obtained infrared IR image, color RGB image and depth image
In, can all there be N number of characteristic point.The corresponding depth value of characteristic point in the IR image, refer to if it is determined that be
I-th of (i is the natural number more than or equal to 1, less than or equal to N) characteristic point in the IR image, then utilize the depth image,
Determine depth value of the ith feature point in depth image, and as the ith feature point in the IR image
Depth value.
Step S234, according to the internal structure parameter of the tested equipment of acquisition and the depth value, the IR figure is determined
Characteristic point as in is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Here it is possible to the IR image obtained according to the internal reference of the RGBD equipment, outer ginseng and distortion parameter and step S233
In characteristic point depth value, to determine that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system.
Step S235, it is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
Three-dimensional coordinate in rgb pixel coordinate system determines the image alignment precision of the tested equipment.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection method of image alignment precision again, and Fig. 2 C is
The implementation process schematic diagram three of the detection method of the embodiment of the present application image alignment precision, as shown in Figure 2 C, which comprises
Step S241, tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: infrared IR image, color RGB image and depth image, has pre-set characteristic point on the test pattern;
Step S242, the characteristic point in the IR image is determined;
In some embodiments, the step S242, determine characteristic point in the IR image after, the method is also wrapped
It includes: using the IR distortion parameter obtained, distortion being carried out to the characteristic point in the IR image and is handled;Wherein, the IR distortion
Parameter is the corresponding camera distortion parameter of IR image.
Step S243, using the depth image, the corresponding depth value of characteristic point in the IR image is determined;
Step S244, according to the first structure parameter of acquisition and the depth value, the characteristic point in the IR image is determined
Three-dimensional coordinate in IR camera coordinates system;Wherein, the first structure parameter, for showing IR pixel coordinate system and IR camera
Projection relation between coordinate system;
Here, the first structure parameter can be the internal reference of RGBD camera, for determining IR pixel coordinate system and IR phase
Projection relation between machine coordinate system.
Step S245, according to the characteristic point in the second structural parameters of acquisition and the IR image in IR camera coordinates system
Three-dimensional coordinate, determine that the characteristic point in the IR image is mapped to the three-dimensional coordinate in RGB camera coordinate system;Second knot
Structure parameter, for showing the projection relation between IR camera coordinates system and RGB camera coordinate system;
Here, second structural parameters can be the outer ginseng of RGBD camera, for determining IR camera coordinates system and RGB phase
Projection relation between machine coordinate system.
Step S246, RGB camera is mapped to according to the characteristic point in the third structural parameters of acquisition and the IR image to sit
Three-dimensional coordinate in mark system, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;It is described
Third structural parameters are used to show the projection relation between rgb pixel coordinate system and RGB camera coordinate system;
Here, the third structural parameters can be the internal reference of RGBD camera, for determining rgb pixel coordinate system and RGB
Projection relation between camera coordinates system.
Step S247, characteristic point corresponding with the IR image in the RGB image is determined;
In some embodiments, the step S247, determine characteristic point corresponding with the IR image in the RGB image
Later, the method also includes: using obtain RGB distortion parameter, the characteristic point in the RGB image is carried out at distortion
Reason;Wherein, the RGB distortion parameter is the corresponding camera distortion parameter of RGB image.
Step S248, the coordinate and the characteristic point in the IR image for determining the corresponding characteristic point are mapped to RGB picture
The difference of three-dimensional coordinate in plain coordinate system;
Step S249, according to the difference, the image alignment precision of the tested equipment is determined.
In some embodiments, the step S249, according to the difference, determine the image alignment of the tested equipment
Precision, comprising:
The step S2491, according to the difference of all characteristic points, determine the corresponding standard deviation of the difference of all characteristic points,
Average value and maximum value;
The step S2492, according to the standard deviation, average value and maximum value, determine the image of the tested equipment
Alignment accuracy.
In the embodiment of the present application, there is pre-set N number of characteristic point on the test pattern, therefore, the difference includes
The difference of the coordinate of characteristic point after multiple mappings, and then can pass through the difference of the coordinate of the multiple characteristic point of determination
Standard deviation, average value and maximum value etc., to determine the image alignment precision of the tested equipment.For example, the multiple feature
The average value of the difference of point is greater than preset threshold, it may be considered that the image alignment precision of the RGBD equipment is low, conversely, described
The average value of the difference of multiple characteristic points is less than or equal to preset threshold, it may be considered that the image alignment precision of the RGBD equipment
It is high.It is of course also possible to directly quantitatively determine the image of the RGBD equipment according to the standard deviation, average value and maximum value
Alignment accuracy.
In the embodiment of the present application, by obtaining tested equipment to the shooting result of the test pattern in detection device,
In, the shooting result includes: infrared IR image, color RGB image and depth image, is preset on the test pattern
Characteristic point;Determine the characteristic point in the IR image;Using the depth image, the characteristic point pair in the IR image is determined
The depth value answered;According to the first structure parameter of acquisition and the depth value, determine the characteristic point in the IR image in IR phase
Three-dimensional coordinate in machine coordinate system;According to the characteristic point in the second structural parameters of acquisition and the IR image in IR camera coordinates
Three-dimensional coordinate in system determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in RGB camera coordinate system;According to obtaining
The characteristic point in third structural parameters and the IR image taken is mapped to the three-dimensional coordinate in RGB camera coordinate system, determines institute
State the three-dimensional coordinate that the characteristic point in IR image is mapped in rgb pixel coordinate system;It determines in the RGB image and schemes with the IR
As corresponding characteristic point;The coordinate and the characteristic point in the IR image for determining the corresponding characteristic point are mapped to rgb pixel
The difference of three-dimensional coordinate in coordinate system;According to the difference, the image alignment precision of the tested equipment is determined, in this way,
The image alignment accuracy checking method that a kind of applicability is extensive, high-efficient is provided.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection method of image alignment precision, the side again
Method includes:
Step S301, shooting IR image, RGB image and depth image in shorter time interval;
Step S302, IR image characteristic point detects;
Step S303, IR image characteristic point coordinate goes distortion to handle;
Step S304, IR camera coordinates system three-dimensional coordinate is obtained in conjunction with IR internal reference and the depth value in respective coordinates region;
Step S305, mapping three-dimensional point of the IR characteristic point in RGB camera coordinate system is obtained in conjunction with ginseng outside IR-RGB;
Step S306, mapping point of the IR characteristic point in rgb pixel coordinate system is obtained in conjunction with RGB internal reference;
Step S307, RGB image characteristic point detects, and goes distortion to handle on characteristic point coordinate using RGB distortion parameter;
Step S308, the undistorted characteristic point coordinate of RGB and IR mapping point identical point coordinates difference are calculated, and calculates the difference
It is worth standard deviation, average value and maximum value and carries out thresholding control.
Fig. 3 is the implementation process schematic diagram four of the detection method of the embodiment of the present application image alignment precision, and Fig. 3 is simpler
Legibly show image alignment accuracy checking method described in above-mentioned steps S301 to step S308.As shown in figure 3, needing first
Obtain the shooting result of tested equipment: depth image, IR image and RGB image.Then, described image is grasped as follows
Make: step S311, IR image detection characteristic point;Step S312, characteristic point coordinate goes distortion to handle;Step S313, in conjunction with depth
Image obtains IR camera coordinates system three-dimensional coordinate;Step S314, RGB camera coordinate system three-dimensional coordinate;Step S315, IR feature
Point coordinate is in rgb pixel coordinate system mapping point point;Step S316, RGB image characteristic point detects;Step S317, characteristic point is sat
Mark goes distortion to handle;Step S318, the undistorted pixel coordinate system coordinate of RGB image;Step S319, mapping point and actual point are obtained
Coordinate distance asks standard deviation maximum value and average value.In this way, first carrying out the detection of IR image characteristic point, depth image is recycled, is obtained
To IR image characteristic point coordinate rgb pixel coordinate system mapping point point.Then, it is sat with the undistorted pixel of RGB image
Mark system in coordinate be compared, obtain the coordinate distance between mapping point and actual point, recycle the distance standard deviation,
Maximum value and average value, so that it may determine the alignment accuracy of image.
The image alignment accuracy checking method provided in the embodiment of the present application can be equally used for carrying TOF camera
RGBD system evaluation needs to replace with IR image therein the Confidence of TOF camera acquisition in above-mentioned flow and method
Image (i.e. the infrared image of TOF camera acquisition).This method is mainly used for pair of evaluation test structure light depth map and RGB image
Neat precision.RGBD system based on structure light is needed for depth point cloud to be aligned with RGB image when in use, that is, is commonly called as
Textures, so in the RGBD equipment generating process based on structure light, after the alignment calibration for finishing depth+RGB, Wo Menxu
Whether the structure for detecting alignment calibration meets the requirements, and this method obtains depth point by detection IR characteristic point, and using depth
Cloud, and the inside and outside ginseng obtained by alignment calibration, are converted into the same coordinate system for IR image and RGB image coordinate points, and calculate
Its difference, so that we can control with objective quantification alignment accuracy, when facilitating batch production to mould group alignment accuracy consistency.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection device of image alignment precision, the device packet
Each component included by each module included by included each unit and each unit and each module is included, electricity can be passed through
Processor in sub- equipment is realized;Certainly it can also be realized by specific logic circuit;In the process of implementation, processor can
Think CPU (Central Processing Unit, central processing unit), MPU (Microprocessor Unit, micro process
Device), DSP (Digital Signal Processing, digital signal processor) or FPGA (Field Programmable
Gate Array, field programmable gate array) etc..
Fig. 4 is the composed structure schematic diagram of the detection device of the embodiment of the present application image alignment precision, as shown in figure 4, institute
Stating device 400 includes:
Acquiring unit 401, for obtaining tested equipment to the shooting result of the test pattern in detection device, wherein
The shooting result includes: IR image, RGB image and depth image, there is pre-set characteristic point on the test pattern;
First determination unit 402, for according in the IR image characteristic point and the depth image, determine the IR
Characteristic point in image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Second determination unit 403, for the spy in the coordinate and the IR image according to the characteristic point in the RGB image
The three-dimensional coordinate that sign point is mapped in rgb pixel coordinate system, determines the image alignment precision of the tested equipment.
In some embodiments, first determination unit 402, comprising:
First determining module, for determining the characteristic point in the IR image;
First determining module is also used to internal structure parameter and the depth map according to the tested equipment of acquisition
Picture determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system.
In some embodiments, second determination unit 403, comprising:
Second determining module, for determining characteristic point corresponding with the IR image in the RGB image;
Second determining module, the coordinate for being also used to determine the corresponding characteristic point and the feature in the IR image
The difference for the three-dimensional coordinate that point is mapped in rgb pixel coordinate system;
Second determining module is also used to determine the image alignment precision of the tested equipment according to the difference.
In some embodiments, first determining module, comprising:
First determines component, for utilizing the depth image, determines the corresponding depth of characteristic point in the IR image
Value;
Described first determines component, is also used to the internal structure parameter and the depth according to the tested equipment of acquisition
Value, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system.
In some embodiments, described first component is determined, comprising:
First determine subassembly, for according to acquisition first structure parameter and the depth value, determine the IR image
In three-dimensional coordinate of the characteristic point in IR camera coordinates system;Wherein, the first structure parameter, for showing IR pixel coordinate
Projection relation between system and IR camera coordinates system;
Described first determines subassembly, the characteristic point being also used in the second structural parameters and the IR image according to acquisition
Three-dimensional coordinate in IR camera coordinates system determines that the characteristic point in the IR image is mapped to three in RGB camera coordinate system
Tie up coordinate;Second structural parameters, for showing the projection relation between IR camera coordinates system and RGB camera coordinate system;
Described first determines subassembly, the characteristic point being also used in the third structural parameters and the IR image according to acquisition
The three-dimensional coordinate being mapped in RGB camera coordinate system determines that the characteristic point in the IR image is mapped in rgb pixel coordinate system
Three-dimensional coordinate;The third structural parameters are used to show that the projection between rgb pixel coordinate system and RGB camera coordinate system to be closed
System.
In some embodiments, described device further include:
First removes distortion unit, for being gone to the characteristic point in the IR image using the IR distortion parameter obtained
Distortion processing;Wherein, the IR distortion parameter is the corresponding camera distortion parameter of IR image;
Second removes distortion unit, for being carried out to the characteristic point in the RGB image using the RGB distortion parameter obtained
Distortion is gone to handle;Wherein, the RGB distortion parameter is the corresponding camera distortion parameter of RGB image.
In some embodiments, second determining module, comprising:
Second determines that component determines the corresponding standard of the difference of all characteristic points for the difference according to all characteristic points
Difference, average value and maximum value;
Described second determines component, is also used to determine that described be detected sets according to the standard deviation, average value and maximum value
Standby image alignment precision.
Based on embodiment above-mentioned, the embodiment of the present application provides a kind of detection device, and Fig. 5 is that the embodiment of the present application detection is set
Standby composed structure schematic diagram one, as shown in figure 5, the detection device 500 includes:
Test suite 501 is contacted with backlight 502, and the test pattern being pre-designed is provided on the test suite,
So that the detection device 500 can be realized to the tested equipment when tested equipment shoots the test pattern
The function of image alignment accuracy detection;
Backlight 502 enables the tested equipment to obtain the test chart for issuing visible or infrared light
IR image, RGB image and the depth image of case;
Processor 503, for executing following steps:
Tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting result includes:
IR image, RGB image and depth image have pre-set characteristic point on the test pattern;
According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to
Three-dimensional coordinate in rgb pixel coordinate system;
Rgb pixel is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image to sit
Three-dimensional coordinate in mark system, determines the image alignment precision of the tested equipment.
In the embodiment of the present application, it is provided with and is pre-designed on the first face for being contacted on the test suite with the backlight
Test pattern, second face opposite with the contact surface has diffusing characteristic diffuser on the test suite.
Fig. 6 is the composed structure schematic diagram two of the embodiment of the present application detection device, as shown in fig. 6, the detection device 600
It include: test suite 601 and backlight 602, in which: backlight 602 is double-colored light source, can beat visible light or beat infrared
Light.Test suite 601 designs for half-reflection and half-transmission, and the one side close to RGBD camera 603 is diffusing reflection pattern-free blank sheet of paper, close to backlight
The one side of plate prints the pattern that we are pre-designed.
The embodiment of the present application provides the image alignment precision testing device that a kind of applicability is extensive, high-efficient, wherein inspection
The evaluation method that measurement equipment is related to is high-efficient, applicability is extensive, it can also be used to carry the evaluation of the RGBD system of TOF camera, such as
This, is conducive to the batch production of the detection device, and single detection device is also simple to operation.
The description of apparatus above, apparatus embodiments, be with the description of above method embodiment it is similar, have with method reality
Apply the similar beneficial effect of example.For undisclosed technical detail in the application device, apparatus embodiments, the application side is please referred to
The description of method embodiment and understand.
It should be noted that in the embodiment of the present application, if realizing above-mentioned image pair in the form of software function module
The detection method of neat precision, and when sold or used as an independent product also can store and computer-readable deposit at one
In storage media.Based on this understanding, the technical solution of the embodiment of the present application substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which is stored in a storage medium, including
Some instructions are used so that an electronic equipment (can be personal computer, server etc.) executes each embodiment institute of the application
State all or part of method.And storage medium above-mentioned include: USB flash disk, mobile hard disk, ROM (Read Only Memory, only
Read memory), the various media that can store program code such as magnetic or disk.In this way, the embodiment of the present application is not limited to
Any specific hardware and software combines.
Accordingly, the embodiment of the present application provides a kind of detection device, including memory and processor, the memory storage
There is a computer program that can be run on a processor, the processor is realized when executing described program to be provided in above-described embodiment
Step in the detection method of image alignment precision.
Accordingly, the embodiment of the present application provides a kind of readable storage medium storing program for executing, is stored thereon with computer program, the computer
The step in the detection method of above-mentioned image alignment precision is realized when program is executed by processor.
It need to be noted that: the description of medium stored above and apparatus embodiments, with retouching for above method embodiment
It is similar for stating, and has with embodiment of the method similar beneficial effect.For in the application storage medium and apparatus embodiments not
The technical detail of disclosure please refers to the description of the application embodiment of the method and understands.
It should be noted that Fig. 7 is a kind of hardware entities schematic diagram of the embodiment of the present application detection device, as shown in fig. 7,
The hardware entities of the detection device 700 include: processor 701, communication interface 702 and memory 703, in which:
The overall operation of the usually control detection device 700 of processor 701.
Communication interface 702 can make detection device 700 pass through network and other terminals or server communication.
Memory 703 is configured to store the instruction and application that can be performed by processor 701, can also cache device to be processed
701 and detection device 700 in each module it is to be processed or processed data (for example, image data, audio data, voice
Communication data and video communication data), FLASH (flash memory) or RAM (Random Access Memory, random visit can be passed through
Ask memory) it realizes.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only
A kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can combine, or
It is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each composition portion
Mutual coupling or direct-coupling or communication connection is divided to can be through some interfaces, the INDIRECT COUPLING of equipment or unit
Or communication connection, it can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit
The component shown can be or may not be physical unit, it can and it is in one place, it may be distributed over multiple network lists
In member;Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, can be fully integrated into a processing module in each functional unit in each embodiment of the application, it can also
To be each unit individually as a unit, can also be integrated in one unit with two or more units;It is above-mentioned
Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.This
Field those of ordinary skill, which is understood that, realizes that all or part of the steps of above method embodiment can be by program instruction phase
The hardware of pass is completed, and program above-mentioned can be stored in a computer readable storage medium, which when being executed, holds
Row step including the steps of the foregoing method embodiments.
Disclosed method in several embodiments of the method provided herein, in the absence of conflict can be any group
It closes, obtains new embodiment of the method.
Disclosed feature in several product embodiments provided herein, in the absence of conflict can be any group
It closes, obtains new product embodiments.
Disclosed feature in several methods provided herein or apparatus embodiments, in the absence of conflict can be with
Any combination obtains new embodiment of the method or apparatus embodiments.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application should be based on the protection scope of the described claims.
Claims (12)
1. a kind of detection method of image alignment precision, which is characterized in that the described method includes:
Tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting result includes: infrared
IR image, color RGB image and depth image have pre-set characteristic point on the test pattern;
According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to RGB
Three-dimensional coordinate in pixel coordinate system;
Rgb pixel coordinate system is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
In three-dimensional coordinate, determine the image alignment precision of the tested equipment.
2. the method according to claim 1, wherein the characteristic point and the depth according in the IR image
Image is spent, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, comprising:
Determine the characteristic point in the IR image;
According to the internal structure parameter of the tested equipment of acquisition and the depth image, the characteristic point in the IR image is determined
The three-dimensional coordinate being mapped in rgb pixel coordinate system.
3. according to the method described in claim 2, it is characterized in that, the coordinate according to the characteristic point in the RGB image
It is mapped to the three-dimensional coordinate in rgb pixel coordinate system with the characteristic point in the IR image, determines the figure of the tested equipment
As alignment accuracy, comprising:
Determine characteristic point corresponding with the IR image in the RGB image;
Determine that the coordinate of the corresponding characteristic point is mapped to three in rgb pixel coordinate system with the characteristic point in the IR image
Tie up the difference of coordinate;
According to the difference, the image alignment precision of the tested equipment is determined.
4. according to the method described in claim 2, it is characterized in that, the internal structure of the tested equipment according to acquisition is joined
The several and depth image, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, wraps
It includes:
Using the depth image, the corresponding depth value of characteristic point in the IR image is determined;
According to the internal structure parameter of the tested equipment of acquisition and the depth value, determine that the characteristic point in the IR image is reflected
The three-dimensional coordinate being mapped in rgb pixel coordinate system.
5. according to the method described in claim 4, it is characterized in that, the internal structure of the tested equipment according to acquisition is joined
The several and depth value, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system, comprising:
According to the first structure parameter of acquisition and the depth value, determine the characteristic point in the IR image in IR camera coordinates system
In three-dimensional coordinate;Wherein, the first structure parameter, for showing the throwing between IR pixel coordinate system and IR camera coordinates system
Shadow relationship;
According to three-dimensional coordinate of the characteristic point in the second structural parameters of acquisition and the IR image in IR camera coordinates system, really
Characteristic point in the fixed IR image is mapped to the three-dimensional coordinate in RGB camera coordinate system;Second structural parameters are used for table
Projection relation between bright IR camera coordinates system and RGB camera coordinate system;
The three-dimensional seat being mapped to according to the characteristic point in the third structural parameters of acquisition and the IR image in RGB camera coordinate system
Mark, determines that the characteristic point in the IR image is mapped to the three-dimensional coordinate in rgb pixel coordinate system;The third structural parameters are used
In showing the projection relation between rgb pixel coordinate system and RGB camera coordinate system.
6. according to the method described in claim 3, it is characterized in that, after characteristic point in the determination IR image, institute
State method further include:
Using the IR distortion parameter of acquisition, distortion is carried out to the characteristic point in the IR image and is handled;Wherein, the IR distortion
Parameter is the corresponding camera distortion parameter of IR image;
Accordingly, in the determination RGB image after characteristic point corresponding with the IR image, the method also includes:
Using the RGB distortion parameter of acquisition, distortion is carried out to the characteristic point in the RGB image and is handled;Wherein, the RGB
Distortion parameter is the corresponding camera distortion parameter of RGB image.
7. according to the method described in claim 3, determining the tested equipment it is characterized in that, described according to the difference
Image alignment precision, comprising:
According to the difference of all characteristic points, the corresponding standard deviation of the difference of all characteristic points, average value and maximum value are determined;
According to the standard deviation, average value and maximum value, the image alignment precision of the tested equipment is determined.
8. a kind of detection device of image alignment precision, which is characterized in that described device includes:
Acquiring unit, for obtaining tested equipment to the shooting result of the test pattern in detection device, wherein the shooting
Result includes: IR image, RGB image and depth image, there is pre-set characteristic point on the test pattern;
First determination unit, for according in the IR image characteristic point and the depth image, determine in the IR image
Characteristic point be mapped to the three-dimensional coordinate in rgb pixel coordinate system;
Second determination unit is reflected for the characteristic point in the coordinate and the IR image according to the characteristic point in the RGB image
The three-dimensional coordinate being mapped in rgb pixel coordinate system determines the image alignment precision of the tested equipment.
9. a kind of detection device, which is characterized in that the detection device includes:
Test suite is contacted with backlight, and the test pattern being pre-designed is provided on the test suite, so that when tested
When measurement equipment shoots the test pattern, the detection device can be realized the image alignment precision inspection to the tested equipment
The function of survey;
Backlight enables the tested equipment to obtain the IR of the test pattern for issuing visible or infrared light
Image, RGB image and depth image;
Processor, for executing following steps:
Tested equipment is obtained to the shooting result of the test pattern in detection device, wherein the shooting result includes: IR figure
As, RGB image and depth image, there is pre-set characteristic point on the test pattern;
According in the IR image characteristic point and the depth image, determine that the characteristic point in the IR image is mapped to RGB
Three-dimensional coordinate in pixel coordinate system;
Rgb pixel coordinate system is mapped to according to the characteristic point in the coordinate of the characteristic point in the RGB image and the IR image
In three-dimensional coordinate, determine the image alignment precision of the tested equipment.
10. equipment according to claim 9, which is characterized in that contacted on the test suite with the backlight
It is provided with the test pattern being pre-designed on one side, second face opposite with the contact surface has unrestrained anti-on the test suite
Penetrate characteristic.
11. a kind of detection device, including memory and processor, the memory are stored with the calculating that can be run on a processor
Machine program, which is characterized in that the processor realizes the described image alignment of any one of claim 1 to 7 when executing described program
Step in the detection method of precision.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
The step in the detection method of any one of claim 1 to 7 described image alignment accuracy is realized when processor executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910678583.6A CN110378971A (en) | 2019-07-25 | 2019-07-25 | A kind of detection method and device of image alignment precision, equipment, storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910678583.6A CN110378971A (en) | 2019-07-25 | 2019-07-25 | A kind of detection method and device of image alignment precision, equipment, storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110378971A true CN110378971A (en) | 2019-10-25 |
Family
ID=68256119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910678583.6A Pending CN110378971A (en) | 2019-07-25 | 2019-07-25 | A kind of detection method and device of image alignment precision, equipment, storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110378971A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210410A (en) * | 2019-12-31 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Signal lamp state detection method and device |
CN111583317A (en) * | 2020-04-29 | 2020-08-25 | 深圳市优必选科技股份有限公司 | Image alignment method and device and terminal equipment |
CN112184831A (en) * | 2020-09-23 | 2021-01-05 | 深兰自动驾驶研究院(山东)有限公司 | Automatic corresponding calibration method, system and device for RGB image and IR image |
CN113256611A (en) * | 2021-06-21 | 2021-08-13 | 浙江光珀智能科技有限公司 | RGB-D registration precision testing method and device |
CN114066723A (en) * | 2021-11-11 | 2022-02-18 | 贝壳找房(北京)科技有限公司 | Equipment detection method, device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109211264A (en) * | 2017-07-06 | 2019-01-15 | 杭州海康机器人技术有限公司 | Scaling method, device, electronic equipment and the readable storage medium storing program for executing of measuring system |
CN109754427A (en) * | 2017-11-01 | 2019-05-14 | 虹软科技股份有限公司 | A kind of method and apparatus for calibration |
CN109978929A (en) * | 2017-12-28 | 2019-07-05 | 舜宇光学(浙江)研究院有限公司 | The RGB-D image synthesis optimizing system and method for depth information camera module |
-
2019
- 2019-07-25 CN CN201910678583.6A patent/CN110378971A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109211264A (en) * | 2017-07-06 | 2019-01-15 | 杭州海康机器人技术有限公司 | Scaling method, device, electronic equipment and the readable storage medium storing program for executing of measuring system |
CN109754427A (en) * | 2017-11-01 | 2019-05-14 | 虹软科技股份有限公司 | A kind of method and apparatus for calibration |
CN109978929A (en) * | 2017-12-28 | 2019-07-05 | 舜宇光学(浙江)研究院有限公司 | The RGB-D image synthesis optimizing system and method for depth information camera module |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111210410A (en) * | 2019-12-31 | 2020-05-29 | 深圳市优必选科技股份有限公司 | Signal lamp state detection method and device |
CN111583317A (en) * | 2020-04-29 | 2020-08-25 | 深圳市优必选科技股份有限公司 | Image alignment method and device and terminal equipment |
CN111583317B (en) * | 2020-04-29 | 2024-02-09 | 深圳市优必选科技股份有限公司 | Image alignment method and device and terminal equipment |
CN112184831A (en) * | 2020-09-23 | 2021-01-05 | 深兰自动驾驶研究院(山东)有限公司 | Automatic corresponding calibration method, system and device for RGB image and IR image |
CN112184831B (en) * | 2020-09-23 | 2023-06-16 | 深兰自动驾驶研究院(山东)有限公司 | Automatic corresponding calibration method, system and device for RGB image and IR image |
CN113256611A (en) * | 2021-06-21 | 2021-08-13 | 浙江光珀智能科技有限公司 | RGB-D registration precision testing method and device |
CN113256611B (en) * | 2021-06-21 | 2021-12-24 | 浙江光珀智能科技有限公司 | RGB-D registration precision testing method and device |
CN114066723A (en) * | 2021-11-11 | 2022-02-18 | 贝壳找房(北京)科技有限公司 | Equipment detection method, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378971A (en) | A kind of detection method and device of image alignment precision, equipment, storage medium | |
US10791320B2 (en) | Non-uniform spatial resource allocation for depth mapping | |
CN109741405B (en) | Depth information acquisition system based on dual structured light RGB-D camera | |
EP3531066B1 (en) | Three-dimensional scanning method including a plurality of lasers with different wavelengths, and scanner | |
US20200293763A1 (en) | Three-Dimensional Real Face Modeling Method and Three-Dimensional Real Face Camera System | |
Cyganek et al. | An introduction to 3D computer vision techniques and algorithms | |
US9392262B2 (en) | System and method for 3D reconstruction using multiple multi-channel cameras | |
WO2020035002A1 (en) | Methods and devices for acquiring 3d face, and computer readable storage media | |
CN110111262A (en) | A kind of projector distortion correction method, device and projector | |
CN108627092A (en) | A kind of measurement method, system, storage medium and the mobile terminal of package volume | |
US8306323B2 (en) | Method and apparatus for correcting depth image | |
CN110390719A (en) | Based on flight time point cloud reconstructing apparatus | |
CN109190484A (en) | Image processing method, device and image processing equipment | |
JP5633058B1 (en) | 3D measuring apparatus and 3D measuring method | |
CN112184811B (en) | Monocular space structured light system structure calibration method and device | |
CN106991378A (en) | Facial orientation detection method, detection means and electronic installation based on depth | |
CN107463659A (en) | Object search method and its device | |
CN109565577A (en) | Colour correcting apparatus, color calibration system, colour correction hologram, color correcting method and program | |
CN108175535A (en) | A kind of dentistry spatial digitizer based on microlens array | |
CN102022985B (en) | Three dimensional information measuring device | |
CN113610962A (en) | Three-dimensional reconstruction method and related equipment | |
CN111757086A (en) | Active binocular camera, RGB-D image determination method and device | |
CN107865473A (en) | Characteristics of human body's range unit and its distance-finding method | |
CN108895979A (en) | The structure optical depth acquisition methods of line drawing coding | |
US11748908B1 (en) | Systems and methods for generating point-accurate three-dimensional models with point-accurate color information from a non-cosited capture |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |
|
RJ01 | Rejection of invention patent application after publication |